The Agent Skills Directory

[PROMPT_INJECTION] (SAFE): The instructions focus on tool-specific workflows. There are no attempts to bypass safety filters, extract system prompts, or override the agent's core safety instructions.
[DATA_EXFILTRATION] (SAFE): No commands for accessing sensitive local files (e.g., SSH keys, env files) or exfiltrating data to external domains were detected.
[EXTERNAL_DOWNLOADS] (LOW): The skill utilizes uv add to manage dependencies. While this involves downloading packages from PyPI, it is the standard and intended functionality of a package management skill. No untrusted or malicious sources are specified.
[COMMAND_EXECUTION] (SAFE): Usage of uv run and uv init is restricted to the local development environment for the purpose of project management and does not involve arbitrary or malicious shell execution.
[OBFUSCATION] (SAFE): The content is clear and uses plain markdown. No hidden characters, encoded strings (Base64), or homoglyphs were identified.
[INDIRECT_PROMPT_INJECTION] (SAFE): The skill does not demonstrate an attack surface for ingesting untrusted external data (like web scraping or email processing) and acting upon embedded instructions.

python-uv-project-setup